import { RealtimeClient } from '@openai/realtime-api-beta';

const client = new RealtimeClient({ apiKey: process.env.OPENAI_API_KEY });

// Can set parameters ahead of connecting, either separately or all at once
client.updateSession({ instructions: 'You are a great, upbeat friend.' });
client.updateSession({ voice: 'alloy' });
client.updateSession({
  turn_detection: { type: 'none' }, // or 'server_vad'
  input_audio_transcription: { model: 'whisper-1' },
});

// Set up event handling
client.on('conversation.updated', (event) => {
  const { item, delta } = event;
  const items = client.conversation.getItems();
  /**
   * item is the current item being updated
   * delta can be null or populated
   * you can fetch a full list of items at any time
   */
});

// Connect to Realtime API
await client.connect();

// Send a item and triggers a generation
client.sendUserMessageContent([{ type: 'input_text', text: `How are you?` }]);

import { RealtimeClient } from '@openai/realtime-api-beta';

const client = new RealtimeClient({
  apiKey: process.env.OPENAI_API_KEY,
  dangerouslyAllowAPIKeyInBrowser: true,
});

const client = new RealtimeClient({ url: RELAY_SERVER_URL });

client.sendUserMessageContent([{ type: 'input_text', text: `How are you?` }]);
// or (empty audio)
client.sendUserMessageContent([
  { type: 'input_audio', audio: new Int16Array(0) },
]);

// Send user audio, must be Int16Array or ArrayBuffer
// Default audio format is pcm16 with sample rate of 24,000 Hz
// This populates 1s of noise in 0.1s chunks
for (let i = 0; i < 10; i++) {
  const data = new Int16Array(2400);
  for (let n = 0; n < 2400; n++) {
    const value = Math.floor((Math.random() * 2 - 1) * 0x8000);
    data[n] = value;
  }
  client.appendInputAudio(data);
}
// Pending audio is committed and model is asked to generate
client.createResponse();

// We can add tools as well, with callbacks specified
client.addTool(
  {
    name: 'get_weather',
    description:
      'Retrieves the weather for a given lat, lng coordinate pair. Specify a label for the location.',
    parameters: {
      type: 'object',
      properties: {
        lat: {
          type: 'number',
          description: 'Latitude',
        },
        lng: {
          type: 'number',
          description: 'Longitude',
        },
        location: {
          type: 'string',
          description: 'Name of the location',
        },
      },
      required: ['lat', 'lng', 'location'],
    },
  },
  async ({ lat, lng, location }) => {
    const result = await fetch(
      `https://api.open-meteo.com/v1/forecast?latitude=${lat}&longitude=${lng}&current=temperature_2m,wind_speed_10m`,
    );
    const json = await result.json();
    return json;
  },
);

client.updateSession({
  tools: [
    {
      type: 'function',
      name: 'get_weather',
      description:
        'Retrieves the weather for a given lat, lng coordinate pair. Specify a label for the location.',
      parameters: {
        type: 'object',
        properties: {
          lat: {
            type: 'number',
            description: 'Latitude',
          },
          lng: {
            type: 'number',
            description: 'Longitude',
          },
          location: {
            type: 'string',
            description: 'Name of the location',
          },
        },
        required: ['lat', 'lng', 'location'],
      },
    },
  ],
});

client.on('conversation.updated', ({ item, delta }) => {
  if (item.type === 'function_call') {
    // do something
    if (delta.arguments) {
      // populating the arguments
    }
  }
});

client.on('conversation.item.completed', ({ item }) => {
  if (item.type === 'function_call') {
    // your function call is complete, execute some custom code
  }
});

// id is the id of the item currently being generated
// sampleCount is the number of audio samples that have been heard by the listener
client.cancelResponse(id, sampleCount);

// manually send a function call output
client.realtime.send('conversation.item.create', {
  item: {
    type: 'function_call_output',
    call_id: 'my-call-id',
    output: '{function_succeeded:true}',
  },
});
client.realtime.send('response.create');

// errors like connection failures
client.on('error', (event) => {
  // do thing
});

// in VAD mode, the user starts speaking
// we can use this to stop audio playback of a previous response if necessary
client.on('conversation.interrupted', () => {
  /* do something */
});

// includes all changes to conversations
// delta may be populated
client.on('conversation.updated', ({ item, delta }) => {
  // get all items, e.g. if you need to update a chat window
  const items = client.conversation.getItems();
  switch (item.type) {
    case 'message':
      // system, user, or assistant message (item.role)
      break;
    case 'function_call':
      // always a function call from the model
      break;
    case 'function_call_output':
      // always a response from the user / application
      break;
  }
  if (delta) {
    // Only one of the following will be populated for any given event
    // delta.audio = Int16Array, audio added
    // delta.transcript = string, transcript added
    // delta.arguments = string, function arguments added
  }
});

// only triggered after item added to conversation
client.on('conversation.item.appended', ({ item }) => {
  /* item status can be 'in_progress' or 'completed' */
});

// only triggered after item completed in conversation
// will always be triggered after conversation.item.appended
client.on('conversation.item.completed', ({ item }) => {
  /* item status will always be 'completed' */
});

// all events, can use for logging, debugging, or manual event handling
client.on('realtime.event', ({ time, source, event }) => {
  // time is an ISO timestamp
  // source is 'client' or 'server'
  // event is the raw event payload (json)
  if (source === 'server') {
    doSomething(event);
  }
});